INDEX

Explanations

words related to accepting or acknowledging something

oai_token-act-pair · gpt-3.5-turbo

variations of the word "account."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vous

-0.90

 Abyssal

-0.73

 Alley

-0.72

etsk

-0.72

 Dare

-0.70

enegger

-0.69

 Franks

-0.69

 Keynes

-0.68

DonaldTrump

-0.66

 Abyss

-0.64

POSITIVE LOGITS

reditation

1.19

redits

1.07

ursed

0.97

ented

0.97

redit

0.96

rete

0.95

oustic

0.94

ropri

0.94

redited

0.93

oun

0.92

Activations Density 0.015%

words related to accepting or acknowledging something

variations of the word "account."

No Comments

No Known Activations